nanocode/it_automation_enhanced/scripts/test_fixes.py

#!/usr/bin/env python3
"""
测试修复效果
1. 测试ZIP包是否包含图片
2. 测试小红书内容是否去掉原文链接
"""

import os
import sys
import zipfile
import tempfile
import json

def test_zip_with_images():
    """测试ZIP包是否包含图片"""
    print("📦 测试ZIP包图片修复...")
    
    try:
        sys.path.append("/home/ubuntu/nanocode/it_automation_enhanced/scripts")
        from email_with_attachments import EmailWithAttachments
        
        # 测试数据
        test_article = {
            'id': 99,
            'title': '测试修复效果',
            'source': 'Test',
            'word_count': 500,
            'publish_date': '2026-03-19',
            'url': 'https://example.com/test'
        }
        
        test_markdown = "# 测试文章\n\n测试ZIP包图片修复效果。"
        
        # 创建ZIP包
        sender = EmailWithAttachments()
        zip_path = sender.create_zip_package(test_article, test_markdown)
        
        if not zip_path:
            print("❌ ZIP包创建失败")
            return False
        
        print(f"✅ ZIP包创建成功: {zip_path}")
        
        # 检查ZIP内容
        with zipfile.ZipFile(zip_path, 'r') as zipf:
            file_list = zipf.namelist()
            print(f"ZIP包内容 ({len(file_list)} 个文件):")
            
            has_images = False
            for file in file_list:
                print(f"  - {file}")
                if file.startswith('images/'):
                    has_images = True
            
            if has_images:
                print("✅ ZIP包包含图片文件")
            else:
                print("❌ ZIP包不包含图片文件")
            
            # 检查图片文件大小
            for file in file_list:
                if file.startswith('images/'):
                    info = zipf.getinfo(file)
                    print(f"  图片文件: {file} ({info.file_size:,} 字节)")
        
        # 清理测试文件
        if os.path.exists(zip_path):
            os.remove(zip_path)
            print(f"清理测试文件: {zip_path}")
        
        return True
        
    except Exception as e:
        print(f"❌ 测试失败: {e}")
        return False

def test_xiaohongshu_content():
    """测试小红书内容是否去掉原文链接"""
    print("\n📱 测试小红书内容修复...")
    
    try:
        sys.path.append("/home/ubuntu/nanocode/it_automation_enhanced/scripts")
        from xiaohongshu_multi_image import XiaohongshuMultiImagePublisher
        
        # 测试数据
        test_title = "测试文章标题"
        test_content = "这是一篇测试文章的内容。原文链接: https://example.com/article"
        test_tags = ["测试", "技术"]
        
        # 创建发布器
        publisher = XiaohongshuMultiImagePublisher()
        
        # 测试文本分页
        pages = publisher.split_text_to_pages(test_content)
        print(f"文本分页结果: {len(pages)} 页")
        
        # 检查内容是否包含原文链接
        content_has_url = "原文链接:" in test_content or "https://" in test_content
        print(f"原始内容包含原文链接: {content_has_url}")
        
        # 测试过滤逻辑
        import re
        test_preview = test_content[:200] + "..." if len(test_content) > 200 else test_content
        filtered_preview = re.sub(r'原文链接:.*?(?=\n|$)', '', test_preview)
        filtered_preview = re.sub(r'https?://\S+', '', filtered_preview)
        filtered_preview = re.sub(r'\n\s*\n', '\n\n', filtered_preview).strip()
        
        filtered_has_url = "原文链接:" in filtered_preview or "https://" in filtered_preview
        print(f"过滤后内容包含原文链接: {filtered_has_url}")
        
        if filtered_has_url:
            print("❌ 过滤逻辑可能有问题")
            print(f"原始预览: {test_preview[:50]}...")
            print(f"过滤后预览: {filtered_preview[:50]}...")
            return False
        else:
            print("✅ 过滤逻辑正常工作")
            print(f"过滤后预览: {filtered_preview[:50]}...")
            return True
            
    except Exception as e:
        print(f"❌ 测试失败: {e}")
        return False

def test_manual_script():
    """测试手动脚本的内容"""
    print("\n📝 测试手动脚本修复...")
    
    try:
        # 读取手动测试脚本
        script_path = "/home/ubuntu/nanocode/it_automation_enhanced/scripts/manual_full_test.py"
        with open(script_path, 'r', encoding='utf-8') as f:
            content = f.read()
        
        # 检查是否包含"原文链接:"
        if "原文链接:" in content:
            # 找到相关内容
            lines = content.split('\n')
            for i, line in enumerate(lines):
                if "原文链接:" in line:
                    print(f"第 {i+1} 行: {line.strip()}")
                    # 检查上下文
                    for j in range(max(0, i-2), min(len(lines), i+3)):
                        print(f"  {j+1}: {lines[j].strip()}")
            
            print("❌ 手动脚本可能仍然包含原文链接")
            return False
        else:
            print("✅ 手动脚本已去掉原文链接")
            return True
            
    except Exception as e:
        print(f"❌ 测试失败: {e}")
        return False

def test_main_scheduler():
    """测试主调度脚本的内容"""
    print("\n⏰ 测试主调度脚本修复...")
    
    try:
        # 读取主调度脚本
        script_path = "/home/ubuntu/nanocode/it_automation_enhanced/scripts/main_scheduler_complete.sh"
        with open(script_path, 'r', encoding='utf-8') as f:
            content = f.read()
        
        # 检查是否包含"原文链接:"
        if "原文链接:" in content:
            # 找到相关内容
            lines = content.split('\n')
            for i, line in enumerate(lines):
                if "原文链接:" in line:
                    print(f"第 {i+1} 行: {line.strip()}")
            
            print("❌ 主调度脚本可能仍然包含原文链接")
            return False
        else:
            print("✅ 主调度脚本已去掉原文链接")
            return True
            
    except Exception as e:
        print(f"❌ 测试失败: {e}")
        return False

def main():
    """主函数"""
    print("=" * 60)
    print("🔧 测试修复效果")
    print("=" * 60)
    
    results = []
    
    # 测试1: ZIP包图片
    print("\n1️⃣ 测试ZIP包图片修复...")
    zip_result = test_zip_with_images()
    results.append(("ZIP包图片", zip_result))
    
    # 测试2: 小红书内容
    print("\n2️⃣ 测试小红书内容修复...")
    xhs_result = test_xiaohongshu_content()
    results.append(("小红书内容", xhs_result))
    
    # 测试3: 手动脚本
    print("\n3️⃣ 测试手动脚本修复...")
    manual_result = test_manual_script()
    results.append(("手动脚本", manual_result))
    
    # 测试4: 主调度脚本
    print("\n4️⃣ 测试主调度脚本修复...")
    scheduler_result = test_main_scheduler()
    results.append(("主调度脚本", scheduler_result))
    
    # 结果总结
    print("\n" + "=" * 60)
    print("📋 修复测试结果")
    print("=" * 60)
    
    all_passed = True
    for test_name, result in results:
        status = "✅ 通过" if result else "❌ 失败"
        print(f"{test_name}: {status}")
        if not result:
            all_passed = False
    
    print("\n" + "=" * 60)
    if all_passed:
        print("🎉 所有修复测试通过！")
        print("问题已成功修复：")
        print("1. ✅ ZIP包现在包含图片（占位图片）")
        print("2. ✅ 小红书内容已去掉原文链接")
        return 0
    else:
        print("⚠️ 部分修复测试失败，请检查")
        return 1

if __name__ == "__main__":
    sys.exit(main())